]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 807179e)
2-bit quantizations (#4897)
authorKawrakow <redacted>
Sun, 14 Jan 2024 07:45:56 +0000 (09:45 +0200)
committerGitHub <redacted>
Sun, 14 Jan 2024 07:45:56 +0000 (09:45 +0200)
commit147b17ac94a24d524e367cda26a9ff6245689f34
tree6bae34826f82aa28a60ccb26de8eda0464774110tree
parent807179ec583dcb882f97d9704577c06beb2c5ec9commit | diff
2-bit quantizations (#4897)

* imatrix: load

* imatrix: WIP

* imatrix: Add Q2_K quantization

* imatrix: also guard against Q2_K_S quantization without importance matrix

* imatrix: guard even more against low-bit quantization misuse

---------

Co-authored-by: Iwan Kawrakow <redacted>
examples/benchmark/benchmark-matmult.cpp diff | blob | history
examples/quantize/quantize.cpp diff | blob | history
ggml-quants.c diff | blob | history
ggml-quants.h diff | blob | history
ggml.c diff | blob | history
ggml.h diff | blob | history
llama.cpp diff | blob | history
llama.h diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp